Intel Corporation

Other

Amit Gradstein

Zeev Sperber

Robert Valentine

Simon Rubanovich

Mark Jay Charney

Elmoustapha Ould-Ahmed-Vall

Jesus Corbal

Alexander F Heinecke

Menachem Adelman

Bret L Toll

Raanan Sade

Cristina S Anderson

Christopher J Hughes

Benny Eitan

Evangelos Georganas

Jose Yallouz

Milind Baburao Girkar

Seth Abraham

Galina Ryvchin

Thierry Pons

Piotr Majcher

Ittai Anati

Mostafa Hagog

Regev Shemy

Vinodh Gopal

Wajdi K Feghali

Sean M Gulley

Jacob Doweck

Sagi Meller

Ilya Albrekht

Shay Gueron

Naveen K Mellempudi

Daniel Towner

Tal Uliel

Gavri Berger

Ron Schneider

Eyal Hadas

Saeed Kharouf

Thomas D Fletcher

Igor Yanover

Suleyman Sair

Vlad Krasnov

Barukh Ziv

Marius A Cornea-Hasegan

Dhiraj D Kalamkar

Alex Gerber

David M Russinoff

Itai Ravid

Nikita Astafev

Jesus Corbal San Andrian

John W O'Leary

Tomer Weiner

Eyal Oz-Sinay

Boris Ginzburg

Ron Gabor

Joseph Nuzman

Gila Kamhi

Dennis Ryan Bradford

Jonathan Cannon Hall

Brian J Hickmann

Asaf Rubinstein

Dror Markovich

Yuri Gebil

Binh Q Pham

Ziv Aviv

Gregory Pribush

Zelig Wayner

Mrinmay Dutta

Jose-Alejandro Pineiro

Jesus Corbal San Adrian

Yoad Yagil

Guy Bale

Shachar Finkelstein

Ranan Fraer

Christina S Anderson

Moustapha Hagog

Asaf Rubenstein

Onkar P Desai

Binh Pham

Embodiments for a matrix transpose and multiply operation are disclosed. In an embodiment, a processor includes a decoder and execution circuitry. The decoder is to decode an instruction having a format including an opcode field to specify an opcode, a first destination operand field to specify a destination matrix location, a first source operand field to specify a first source matrix location, and a second source operand field to specify a second source matrix location. The execution circuitry is to, in response to the decoded instruction, transpose the first source matrix to generate a transposed first source matrix, perform a matrix multiplication using the transposed first source matrix and the second source matrix to generate a result, and store the result in a destination matrix location.

Matrix transpose and multiply

Systems, methods, and apparatuses relating to performing hashing operations on packed data elements are described. In one embodiment, a processor includes a decode circuit to decode a single instruction into a decoded single instruction, the single instruction including at least one first field that identifies eight 32-bit state elements A, B, C, D, E, F, G, and H for a round according to a SM3 hashing standard and at least one second field that identifies an input message; and an execution circuit to execute the decoded single instruction to: rotate state element C left by 9 bits to form a rotated state element C, rotate state element D left by 9 bits to form a rotated state element D, rotate state element G left by 19 bits to form a rotated state element G, rotate state element H left by 19 bits to form a rotated state element H, perform two rounds according to the SM3 hashing standard on the input message and state element A, state element B, rotated state element C, rotated state element D, state element E, state element F, rotated state element G, and rotated state element H to generate an updated state element A, an updated state element B, an updated state element E, and an updated state element F, and store the updated state element A, the updated state element B, the updated state element E, and the updated state element F into a location specified by the single instruction.

Apparatuses, methods, and systems for hashing instructions

Techniques for scale and reduction of BF16 data elements are described. An exemplary instruction includes fields for an having fields for an opcode, an identification of a location of a first packed data source operand, an identification of a location of a second packed data source operand, and an identification of a packed data destination operand, wherein the opcode is to indicate that execution circuitry is to perform, for each data element position of the packed data source operands, a floating point scale operation of a BF16 data element of the first packed data source by multiplying the data element by a power of 2 value, wherein a value of the exponent of the power of 2 value is a floor value of a BF16 data element of the second packed data source, and store a result of the floating point scale operation into a corresponding data element position of the packed data destination operand.

BFLOAT16 scale and/or reduce instructions

Techniques for converting FP16 data elements to BF8 data elements using a single instruction are described. An exemplary apparatus includes decoder circuitry to decode a single instruction, the single instruction to include a one or more fields to identify a source operand, one or more fields to identify a destination operand, and one or more fields for an opcode, the opcode to indicate that execution circuitry is to convert packed half-precision floating-point data from the identified source to packed bfloat8 data and store the packed bfloat8 data into corresponding data element positions of the identified destination operand; and execution circuitry to execute the decoded instruction according to the opcode to convert packed half-precision floating-point data from the identified source to packed bfloat8 data and store the packed bfloat8 data into corresponding data element positions.

Instructions to convert from FP16 to BF8

Techniques for matrix multiplication are described. In some examples, decode circuitry is to decode a single instruction having fields for an opcode, an indication of a location of a first source operand, an indication of a location of a second source operand, and an indication of a location of a destination operand, wherein the opcode is to indicate that execution circuitry is to at least convert data elements of the first and second source operands from a first floating point representation to a second floating point representation, perform matrix multiplication with the converted data elements, and accumulate results of the matrix multiplication in the destination operand in the first floating point representation; and the execution circuitry is to execute to the decoded instruction as specified by the opcode.

Apparatuses, methods, and systems for instructions for matrix multiplication instructions

Disclosed embodiments relate to computing dot products of nibbles in tile operands. In one example, a processor includes decode circuitry to decode a tile dot product instruction having fields for an opcode, a destination identifier to identify a M by N destination matrix, a first source identifier to identify a M by K first source matrix, and a second source identifier to identify a K by N second source matrix, each of the matrices containing doubleword elements, and execution circuitry to execute the decoded instruction to perform a flow K times for each element (m, n) of the specified destination matrix to generate eight products by multiplying each nibble of a doubleword element (M,K) of the specified first source matrix by a corresponding nibble of a doubleword element (K,N) of the specified second source matrix, and to accumulate and saturate the eight products with previous contents of the doubleword element.

Systems and methods for performing 16-bit floating-point matrix dot product instructions

Embodiments detailed herein relate to systems and methods to store a tile register pair to memory. In one example, a processor includes: decode circuitry to decode a store matrix pair instruction having fields for an opcode and source and destination identifiers to identify source and destination matrices, respectively, each matrix having a PAIR parameter equal to TRUE; and execution circuitry to execute the decoded store matrix pair instruction to store every element of left and right tiles of the identified source matrix to corresponding element positions of left and right tiles of the identified destination matrix, respectively, wherein the executing stores a chunk of C elements of one row of the identified source matrix at a time.

Systems and methods to store a tile register pair to memory

Embodiments detailed herein relate to matrix (tile) operations. For example, decode circuitry to decode an instruction having fields for an opcode and a memory address, and execution circuitry to execute the decoded instruction to store configuration information about usage of storage for two-dimensional data structures at the memory address.

Systems, methods, and apparatuses for matrix operations

Systems, methods, and apparatuses relating to instructions to convert 16-bit floating-point formats are described. In one embodiment, a processor includes fetch circuitry to fetch a single instruction having fields to specify an opcode and locations of a source vector comprising N plurality of 16-bit half-precision floating-point elements, and a destination vector to store N plurality of 16-bit bfloat floating-point elements, the opcode to indicate execution circuitry is to convert each of the elements of the source vector from 16-bit half-precision floating-point format to 16-bit bfloat floating-point format and store each converted element into a corresponding location of the destination vector, decode circuitry to decode the fetched single instruction into a decoded single instruction, and the execution circuitry to respond to the decoded single instruction as specified by the opcode.

Apparatuses, methods, and systems for instructions to convert 16-bit floating-point formats

Embodiments detailed herein relate to systems and methods to load a tile register pair. In one example, a processor includes: decode circuitry to decode a load matrix pair instruction having fields for an opcode and source and destination identifiers to identify source and destination matrices, respectively, each matrix having a PAIR parameter equal to TRUE; and execution circuitry to execute the decoded load matrix pair instruction to load every element of left and right tiles of the identified destination matrix from corresponding element positions of left and right tiles of the identified source matrix, respectively, wherein the executing operates on one row of the identified destination matrix at a time, starting with the first row.

Systems and methods to load a tile register pair

Techniques for performing BF16 FMA in response to an instruction are described. In some examples, an instruction has fields for an opcode, an identification of location of a packed data source/destination operand (a first source), an identification of a location of a second packed data source operand, an identification of a location of a third packed data source operand, and an identification of location of a packed data source/destination operand, wherein the opcode is to indicate operand ordering and that execution circuitry is to, per data element position, perform a BF16 value fused multiply-accumulate operation using the first, second, and third source operands and store a result in a corresponding data element position of the source/destination operand.

BFLOAT16 fused multiply instructions

An apparatus and method for complex matrix conjugation and multiplication. For example, one embodiment of a processor comprises: a decoder to decode a complex matrix conjugation and multiplication instruction including a first source operand to identify a first complex source matrix comprising a first plurality of complex values, a second source operand to identify a second complex source matrix comprising a second plurality of complex values, and a first destination operand to identify a result matrix; execution circuitry to execute the complex matrix conjugation and multiplication instruction, the execution circuitry comprising: matrix conjugation hardware logic to determine a plurality of complex conjugate values corresponding to the first plurality of complex values; transpose hardware logic to transpose the plurality of complex conjugate values to generate a conjugate transpose matrix comprising the complex conjugate values; parallel multiplication circuitry to: multiply real values from the plurality of complex conjugate values of the conjugate transpose matrix with corresponding imaginary values from the second plurality of complex values to generate a first plurality of imaginary products, and multiply imaginary values from the plurality of complex conjugate values of the conjugate transpose matrix with corresponding real values from the second plurality of complex values to generate a second plurality of imaginary products; and addition/subtraction circuitry to add each imaginary product in the first plurality of imaginary products to a corresponding imaginary product in the second plurality of imaginary products to produce a corresponding imaginary component in the result matrix.

Apparatus and method for conjugate transpose and multiply

Systems, methods, and apparatuses relating to a matrix operations accelerator are described. In one embodiment, a processor includes a matrix operations accelerator circuit that includes a two-dimensional grid of fused multiply accumulate circuits that is switchable to a scheduling mode for execution of a decoded single instruction where the matrix operations accelerator circuit loads a first buffer of the two-dimensional grid of fused multiply accumulate circuits from a first plurality of registers that represents a first input two-dimensional matrix, checks if a second buffer of the two-dimensional grid of fused multiply accumulate circuits stores an immediately prior input two-dimension matrix that is the same as a second input two-dimensional matrix from a second plurality of registers that represents the first input two-dimensional matrix, and when the second buffer of the two-dimensional grid of fused multiply accumulate circuits stores the immediately prior input two-dimension matrix, from execution of a previous instruction, that is the same as the second input two-dimensional matrix: prevents reclamation of the second buffer between execution of the previous instruction and the decoded single instruction, performs an operation on the first input two-dimensional matrix from the first buffer and the immediately prior input two-dimension matrix from the second buffer to produce a resultant, and stores the resultant in resultant storage, and when the second buffer of the two-dimensional grid of fused multiply accumulate circuits does not store the immediately prior input two-dimension matrix, from execution of the previous instruction, that is the same as the second input two-dimensional matrix: loads the second input two-dimensional matrix into the second buffer of the two-dimensional grid of fused multiply accumulate circuits, performs the operation on the first input two-dimensional matrix from the first buffer and the second input two-dimension matrix from the second buffer to produce a resultant, and stores the resultant in the resultant storage.

Apparatuses, methods, and systems for instructions of a matrix operations accelerator

Disclosed embodiments relate to computing dot products of nibbles in tile operands. In one example, a processor includes decode circuitry to decode a tile dot product instruction having fields for an opcode, a destination identifier to identify a M by N destination matrix, a first source identifier to identify a M by K first source matrix, and a second source identifier to identify a K by N second source matrix, each of the matrices containing doubleword elements, and execution circuitry to execute the decoded instruction to perform a flow K times for each element (M,N) of the identified destination matrix to generate eight products by multiplying each nibble of a doubleword element (M,K) of the identified first source matrix by a corresponding nibble of a doubleword element (K,N) of the identified second source matrix, and to accumulate and saturate the eight products with previous contents of the doubleword element (M,N).

Systems and methods for computing dot products of nibbles in two tile operands

An apparatus and method for complex matrix multiplication. For example, one embodiment of a processor comprises: a decoder to decode a first complex matrix multiplication instruction; execution circuitry to execute the first complex matrix multiplication instruction, the execution circuitry comprising parallel multiplication circuitry to multiply real values from the first plurality of real and imaginary values with corresponding real values from the second plurality of real and imaginary values to generate a first plurality of real products, to multiply imaginary values from the first plurality of real and imaginary values with corresponding imaginary values from the second plurality of real and imaginary values to generate a second plurality of real products; and addition/subtraction circuitry to subtract each real product in the second plurality of real products from a corresponding real product in the first plurality of real products to produce a corresponding real value in the result matrix. The decoder may also decode and the execution circuitry may execute a second complex matrix multiplication instruction to multiply real and imaginary values from the first plurality with corresponding imaginary and real values, respectively, from the second plurality to generate first and second pluralities of imaginary products, and to add corresponding imaginary products to produce a corresponding imaginary value in the result matrix.

Apparatus and method for complex matrix multiplication

Growing community of inventors

Binyamina, Israel

Amit Gradstein